Papyrus demonstrates solid tool design with clear, action-oriented names (inspect_document, convert_document, convert_to_file, convert_to_chunks, list_directory) and comprehensive descriptions (150-250 chars each). All tools have documented input schemas with typed parameters and descriptions. However, output schemas are not explicitly documented in the visible code, and error handling guidance is minimal. The tool set is well-composed with clear single responsibilities and good parameter naming conventions. Parameter descriptions are detailed and include constraints (e.g., default values, ranges). Missing: explicit output schema documentation, error recovery guidance, and per-tool risk annotations in the MCP registration.

• Add explicit output schema documentation to each tool. Example for inspect_document: 'Returns {format: string, page_count: int, word_count: int, markdown_size: int, warnings: [string]}'.
• Enhance error descriptions with recovery paths. E.g., 'If file format is unsupported, try inspect_document first to confirm the detected format, or convert_to_file to write errors to disk for review.'
• Register tool annotations in MCP: mark convert_to_file with destructiveHint=true (writes to disk), mark all others with readOnlyHint=true.
• Add decision guidance to convert_document and convert_to_chunks descriptions: 'Use convert_document for interactive exploration with pagination; use convert_to_chunks for RAG/embedding pipelines.'
• Document list_directory result limits: 'Returns up to 200 files per call. For larger directories, use recursive=false and iterate through subdirectories, or use convert_to_file to batch-process.'.